Home / Current Issue / Paper 1715930
Sustainable Healthcare System for Pharmaceutical Waste Reduction and Smart Medical Waste Identification
Subject area: Science,Engineering and Technology · Area of research: Sustainable Healthcare System
DOI: https://doi.org/10.64388/IREV9I10-1715930
Abstract
We suggest that health care systems based on AI are more sustainable because they can help with classification and management of waste produced from medical and pharmaceutical sources. In this regard, we make use of machine learning algorithms to automate the categorization of medical waste based upon whether it falls into one of four possible categories: (1) Biodegradable, (2) recyclable, (3) hazardous & (4) pharmaceutical. Computer vision (image processing) techniques and deep learning, in particular CNNs using MobileNetV2 models have been developed to classify various types of medical waste to achieve accurate results. In addition, we have developed a module to analyze past data and provide forecasts regarding future demand for pharmaceutical waste; the module will assist hospitals with decision making related to how much space they should reserve for storing usable pharmaceuticals. Users will also be able to make informed decisions through the user-friendly interface we will provide by employing these techniques within a circular model based upon the principles of sustainability.
How to cite this paper
@article{1715930,
author = {Dr. G. Sangeetha, V. Abhishek, A.E.T. Baskaran, V. Bhargav},
title = {Sustainable Healthcare System for Pharmaceutical Waste Reduction and Smart Medical Waste Identification},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {243-248},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1715930.pdf},
abstract = {We suggest that health care systems based on AI are more sustainable because they can help with classification and management of waste produced from medical and pharmaceutical sources. In this regard, we make use of machine learning algorithms to automate the categorization of medical waste based upon whether it falls into one of four possible categories: (1) Biodegradable, (2) recyclable, (3) hazardous & (4) pharmaceutical. Computer vision (image processing) techniques and deep learning, in particular CNNs using MobileNetV2 models have been developed to classify various types of medical waste to achieve accurate results. In addition, we have developed a module to analyze past data and provide forecasts regarding future demand for pharmaceutical waste; the module will assist hospitals with decision making related to how much space they should reserve for storing usable pharmaceuticals. Users will also be able to make informed decisions through the user-friendly interface we will provide by employing these techniques within a circular model based upon the principles of sustainability.},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1715930}
}